Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Comparative proteomic analysis of seeds before and after dormancy release in Carex schmidtii Meinsh.

Plant biology (Stuttgart, Germany)·2026
Same author

Transient Large-Scale Anisotropy in TeV Cosmic Rays due to an Interplanetary Coronal Mass Ejection.

Physical review letters·2026
Same author

Retraction notice to "Streamflow calculation for medium-to-small rivers in data scarce inland areas" [Sci. Total Environ. 693 (2019) 33571].

The Science of the total environment·2026
Same author

First Detection of Ultrahigh Energy Emission from Gamma-Ray Binary LS I +61° 303.

Physical review letters·2026
Same author

Evidence of Cosmic-Ray Acceleration up to Sub-PeV Energies in the Supernova Remnant IC 443.

Physical review letters·2026
Same author

[Comparison of the efficacy and safety of 36 000 IU vs. 40 000 IU recombinant human erythropoietin for the treatment of cancer-related anemia: a multicenter, open-label, randomized controlled trial].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2026

Related Experiment Video

Updated: Jul 6, 2026

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy
08:17

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Published on: June 7, 2015

15.7K

A Deep-Learning Error Detection System in Radiation Therapy.

P M Kump1, J Xia2, S Yaddanapudi3

  • 1Department of Electrical and Computer Engineering, College of Engineering, Kansas State University, Manhattan, KS, USA.

Annals of Biomedical Research
|January 5, 2024
PubMed
Summary

A new algorithm converts radiation therapy data into heat maps, enabling deep learning to automatically verify treatment sites and prevent patient harm. This method achieved 97.8% accuracy in predicting treatment locations, enhancing safety in radiation oncology.

Keywords:
Deep learningRadiation therapy error detectionTransfer learningTreatment plan data structure

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

1.4K

Related Experiment Videos

Last Updated: Jul 6, 2026

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy
08:17

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Published on: June 7, 2015

15.7K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

1.4K

Area of Science:

  • Medical Physics
  • Artificial Intelligence in Healthcare
  • Radiation Oncology

Background:

  • Radiation therapy errors due to corrupted data can lead to severe patient harm.
  • Current methods for verifying treatment plans are complex and may not catch all errors.
  • Automated verification is crucial for improving patient safety in radiation oncology.

Purpose of the Study:

  • To develop a novel algorithm for structuring radiation therapy plan data.
  • To enable automated verification of treatment sites using deep learning.
  • To enhance the safety and accuracy of radiation therapy delivery.

Main Methods:

  • A new algorithm converts geometric and dose parameters into heat maps representing treatment plan data.
  • Deep learning classifiers, specifically convolutional neural networks (ConvNets), are used to predict treatment sites from these heat maps.
  • The algorithm was evaluated using real-world treatment plan data from head-neck, breast, and prostate cancer patients.

Main Results:

  • The proposed algorithm successfully structured complex treatment plan data into interpretable heat maps.
  • ResNet-18, a ConvNet architecture, achieved the highest accuracy (97.8%) and F-1 score (0.979) in classifying treatment sites.
  • The heat maps retained sufficient information for accurate treatment site prediction, despite using limited plan parameters.

Conclusions:

  • The developed algorithm provides an intuitive and effective method for structuring radiation therapy data for automated verification.
  • Heat map representation combined with deep learning offers a promising approach for detecting errors and improving safety in radiation oncology.
  • This strategy can significantly reduce the risk of patient harm resulting from treatment plan data errors.